OK - it worked! All packages successfully installed via NVMe without the SD card with flashing. Can’t ask for more than this :)
lscpu returns what’s expected and MAXN was shown OOTB (as you’d expect!)
krickert@ubuntu:~$ lscpu
Architecture: aarch64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 6
On-line CPU(s) list: 0-5
Vendor ID: ARM
Model name: Cortex-A78AE
Model: 1
Thread(s) per core: 1
Core(s) per cluster: 3
Socket(s): -
Cluster(s): 2
Stepping: r0p1
CPU max MHz: 1728.0000
CPU min MHz: 115.2000
BogoMIPS: 62.50
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp
asimdhp cpuid asimdrdm lrcpc dcpop asimddp uscat ilrcp
c flagm paca pacg
Caches (sum of all):
L1d: 384 KiB (6 instances)
L1i: 384 KiB (6 instances)
L2: 1.5 MiB (6 instances)
L3: 4 MiB (2 instances)
NUMA:
NUMA node(s): 1
NUMA node0 CPU(s): 0-5
Vulnerabilities:
Gather data sampling: Not affected
Itlb multihit: Not affected
L1tf: Not affected
Mds: Not affected
Meltdown: Not affected
Mmio stale data: Not affected
Retbleed: Not affected
Spec rstack overflow: Not affected
Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Spectre v1: Mitigation; __user pointer sanitization
Spectre v2: Mitigation; CSV2, but not BHB
Srbds: Not affected
Tsx async abort: Not affected
krickert@ubuntu:~$
The the tegrastats:
01-03-2025 00:43:41 RAM 3121/7620MB (lfb 1x4MB) SWAP 0/3810MB (cached 0MB) CPU [7%@729,10%@729,13%@729,8%@729,5%@729,6%@729] EMC_FREQ 3%@2133 GR3D_FREQ 0%@[305] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@49.531C soc2@48.062C soc0@49.093C gpu@49.75C tj@51.156C soc1@51.156C VDD_IN 6309mW/6309mW VDD_CPU_GPU_CV 792mW/792mW VDD_SOC 2023mW/2023mW
01-03-2025 00:43:42 RAM 3121/7620MB (lfb 1x4MB) SWAP 0/3810MB (cached 0MB) CPU [5%@1728,3%@1728,3%@1021,3%@729,0%@729,0%@729] EMC_FREQ 2%@2133 GR3D_FREQ 0%@[305] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@49.312C soc2@48.062C soc0@49.187C gpu@49.718C tj@51.062C soc1@51.062C VDD_IN 5952mW/6131mW VDD_CPU_GPU_CV 554mW/673mW VDD_SOC 2020mW/2022mW
01-03-2025 00:43:43 RAM 3121/7620MB (lfb 1x4MB) SWAP 0/3810MB (cached 0MB) CPU [5%@1587,3%@729,2%@729,3%@729,4%@729,0%@729] EMC_FREQ 2%@2133 GR3D_FREQ 0%@[305] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@49C soc2@48.093C soc0@49.125C gpu@49.625C tj@50.968C soc1@50.968C VDD_IN 5991mW/6084mW VDD_CPU_GPU_CV 594mW/647mW VDD_SOC 2020mW/2021mW
01-03-2025 00:43:44 RAM 3122/7620MB (lfb 1x4MB) SWAP 0/3810MB (cached 0MB) CPU [5%@1728,8%@729,3%@729,3%@729,1%@729,3%@729] EMC_FREQ 2%@2133 GR3D_FREQ 0%@[305] NVDEC off NVJPG off NVJPG1 off VIC off OFA off APE 200 cpu@49.156C soc2@47.906C soc0@49.031C gpu@49.687C tj@50.968C soc1@50.968C VDD_IN 5991mW/6061mW VDD_CPU_GPU_CV 594mW/634mW VDD_SOC 2020mW/2021mW
nvidia-smi:
$ nvidia-smi
Fri Jan 3 00:41:38 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 540.4.0 Driver Version: 540.4.0 CUDA Version: 12.6 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Orin (nvgpu) N/A | N/A N/A | N/A |
| N/A N/A N/A N/A / N/A | Not Supported | N/A N/A |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| No running processes found |
+---------------------------------------------------------------------------------------+
I can attach the logs too, that’s on my other machine and I’ll add that if it helps troubleshoot anyone else.
By the way - I can see that this is a very complicated install. Kudos to your team to set such a complex setup in such a small package! It is impressive. There’s no way I could write this in one swoop - I can see why my manual install wasn’t going to work given the complexity of dependencies.
Thanks for getting me to redo this. Once I got sdkmanager over the hump (turning off bluetooth, using ethernet instead, logging into the machine after startup all seems to have contributed to everything working).
Here’s the output of the install
I already have basic models running and have open-ui running. So it’s working like a charm.
So in the long run, I did follow the directions - I think that the linux host machine - being my intel machine running ubuntu linux - needs to have bluetooth turned off during this process. I also had the nano connectivity done thorough ssh and not the default setting to use the USB serial cable. Regardless, I think I understand enough about the installation now to do this again should the need arise.
Thanks for your prompt replies. Appreciate it.